<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Jev on Darragh Mahns</title><link>https://darraghmahns.com/tags/jev/</link><description>Recent content in Jev on Darragh Mahns</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 18 Sep 2026 12:00:00 -0700</lastBuildDate><atom:link href="https://darraghmahns.com/tags/jev/index.xml" rel="self" type="application/rss+xml"/><item><title>What Jev Could Change About Business Software</title><link>https://darraghmahns.com/posts/what-jev-could-change-about-business-software/</link><pubDate>Fri, 18 Sep 2026 12:00:00 -0700</pubDate><guid>https://darraghmahns.com/posts/what-jev-could-change-about-business-software/</guid><description>&lt;p&gt;&lt;img src="https://darraghmahns.com/images/blog/what-jev-could-change-about-business-software.webp" alt="Stippled halftone artwork from TypeSafe AI&amp;rsquo;s site"&gt;&lt;/p&gt;
&lt;p&gt;An agent watching a shared conversation has to decide whether it should respond. A system collecting product feedback has to work out whether two messages describe the same bug. A tool processing records has to recognize when different descriptions refer to the same thing.&lt;/p&gt;
&lt;p&gt;These decisions come up throughout the software we build at &lt;a href="https://latticepartners.ai" class="external-link" target="_blank" rel="noopener"&gt;Lattice Partners&lt;/a&gt;. They are also where I would want to test Jev.&lt;/p&gt;</description></item></channel></rss>